Early-fusion based pulsar identification with smart under-sampling
| Autor: | Xiao-Ying Zheng, Shi-Chuan Zhang, Tao An, Xiang-Cong Kong, Ling-Yao Chen, Chun-Ling Xu, Yue-Ying Zhou, Bao-Qiang Lao |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Physics
Speedup business.industry media_common.quotation_subject Deep learning FOS: Physical sciences Astronomy and Astrophysics Astrophysics Under sampling Machine learning computer.software_genre Field (computer science) Identification (information) Pulsar Space and Planetary Science Artificial intelligence Astrophysics - Instrumentation and Methods for Astrophysics Function (engineering) F1 score business Instrumentation and Methods for Astrophysics (astro-ph.IM) computer media_common |
| Zdroj: | Research in Astronomy and Astrophysics. 21:257 |
| ISSN: | 1674-4527 |
| DOI: | 10.1088/1674-4527/21/10/257 |
| Popis: | The discovery of pulsars is of great significance in the field of physics and astronomy. As the astronomical equipment produces a large number of pulsar data, an algorithm for automatically identifying pulsars becomes urgent. We propose a deep learning framework for pulsar recognition. In response to the extreme imbalance between positive and negative examples and the hard negative sample issue presented in the High Time Resolution Universe Medlat Training Data, there are two coping strategies in our framework: the smart under-sampling and the improved loss function. We also apply the early-fusion strategy to integrate features obtained from different attributes before classification to improve the performance. To our best knowledge, this is the first study that integrates these strategies and techniques in pulsar recognition. The experiment results show that our framework outperforms previous works with respect to either the training time or F1 score. We can not only speed up the training time by 10 × compared with the state-of-the-art work, but also get a competitive result in terms of F1 score. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|